INDEX

Explanations

mentions of items that can be purchased or acquired, such as products or cars

oai_token-act-pair · gpt-3.5-turbo

references to items for sale or purchases

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xual

-0.95

ĸļ

-0.91

ilial

-0.83

ngth

-0.75

ulty

-0.74

encies

-0.72

icable

-0.70

amination

-0.70

ciplinary

-0.68

ional

-0.68

POSITIVE LOGITS

 groceries

1.19

 cheap

0.98

 cheapest

0.93

 discounted

0.91

 cheaply

0.89

 tickets

0.88

 licences

0.87

 pricey

0.82

 lottery

0.82

 cheaper

0.82

Activations Density 0.191%

mentions of items that can be purchased or acquired, such as products or cars

references to items for sale or purchases

No Comments

No Known Activations